计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
torchforge-rl-training【效率与协作】Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准